Writing Stories with Help from Recurrent Neural Networks

Automated story generation has a long history of pursuit in RNNs are extremely powerful for NLP tasks, having demonstrated artificial intelligence. Early approaches used hand-authored success on tasks like speech recognition (Graves and formal models of a particular story-world domain to generate Jaitly 2014) and machine translation (Sundermeyer et al. narratives pertaining to that domain (Klein, Aeschlimann, 2014). Mikolov et al. (Mikolov et al. 2010) showed that and Balsiger 1973; Lebowitz 1985; Meehan 1977). RNNs encode more accurate language models than traditional With the advent of machine learning, more recent work has n-gram statistics, as measured by performance on a explored how to construct narrative models automatically standard speech recognition task. The simplest RNN architecture from story corpora (Li et al. 2013; McIntyre and Lapata has an input layer, hidden layer, and output layer connected 2009; Swanson and Gordon 2012).